Author Topic: AI solution to detect and track COVID-19  (Read 97 times)

Engr. Md Liakwat Ali Khan

  • Administrator
  • Newbie
  • *****
  • Posts: 1
    • View Profile
AI solution to detect and track COVID-19
« on: April 06, 2020, 05:37:47 AM »
"Research team of Department of Public Health, DIU and Cardio Care Hospital developed and released beta version of AI solution to detect and track COVID-19".
In the absence of specific therapeutic drugs or vaccines for COVID-19, it is essential to detect the disease at an early stage and immediately isolate the infected person from the healthy population. According to the latest guidelines published by the government, the diagnosis of COVID-19 must be confirmed by reverse-transcription polymerase chain reaction (RT-PCR). However, with limitations of sample collection and transportation as well as kit performance, the RT-PCR tests are quite challenging.
In the current situation, COVID-19 patients should be identified quickly so that they can receive appropriate treatment. WHO recommended that early diagnosis of COVID-19 is crucial for disease treatment and control.
We know that radiology can play a crucial role in the diagnosis and identification of patients for observation in the hospital admission or at the screening centre. The most commonly used diagnostic modality is chest radiography.
In a study by team of researchers from Department of Public Health, Cardio-Care Hospital and Artificial Intelligence (AI) Unit of Daffodil International University (DIU) has developed a new diagnostic modality to detect COVID – 19; where the researchers are using AI software to detect Covid-19 by analyzing the soft copy of chest X-ray or images from lung CT scans. By using this AI technology, the health workers/Doctors can instantly diagnose if the suspected person has COVID – 19 or not. Currently, this AI technology can differentiate between COVID 19 and other respiratory illnesses including Pneumonia. Doctors can then follow up with other examinations and lab tests to confirm a diagnosis of the disease. In this research, we found that the sensitivity of this AI modality for COVID-19 infection is 96%.

The researchers have also developed a website for this solution which can be used by any registered/authorized facilities or centres or by any individual doctors who have computer and internet access, from any corner of Bangladesh. Health workers can upload the chest X-ray image to website and instantly get the decision. DIU can offer free online training to all health workers.

Research Team:
1.   Professor Dr. Abu Naser Zafar Ullah; MBBS, MPH (UK), PhD (UK) - Professor of Public Health & Associate Dean, Faculty of Allied Health Sciences, DIU
2.   Engr. Md Liakwat Ali Khan,
3.   Engr. Md Habibur Rahman
4.   Engr. Sheikh Md. Faysal
5.   Dr. ABM Alauddin Chowdhury, Head, Department of Public Health
6.   Md Nasir – Cardio Care Hospital
7.   Md. Mahedi Hasan, Department of Public Health (Administrative Support)বাংলাদেশে-কৃত্রিম-বুদ্ধি.htmlবাংলাদেশে-কৃত্রিম-বুদ্ধি.htmlকরোনা-ভাইরাস-বাংলাদেশেই/কৃত্রিম-বুদ্ধিমত্তা-ব্যবহার-করে-করোনা-শনাক্তকরণ-পদ্ধতি-উদ্ভাবন/print